Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical terms and keywords related to programming and computing contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.94
     myſelf
    -0.93
     houſe
    -0.92
     occaf
    -0.89
     uſed
    -0.87
     themſelves
    -0.87
     itſelf
    -0.87
     raiſ
    -0.86
     pleaſure
    -0.82
     Monfieur
    -0.82
    POSITIVE LOGITS
     module
    0.61
    这个
    0.55
     category
    0.54
     section
    0.53
    AsUp
    0.52
     mode
    0.52
    這個
    0.48
     portion
    0.48
     这个
    0.48
    ArrowToggle
    0.48
    Act Density 1.071%

    No Known Activations